Kling

Kling video models for expressive motion, subject control, and creative clips.

API surface

Operation	Endpoint	Mode
Video generation task	POST /v1/async/videos/generations	Async only

Models

Model id	Notes
kling-3.0-turbo	Text-to-video and image-to-video (first frame only). seconds 3–15.
kling-v3	Text-to-video and image-to-video. seconds 3–15.
kling-v3-omni	Text-to-video and image-to-video with richer providerOptions (video_list, image_with_roles, etc.).

Pricing

Billed as n × seconds × rate(resolution) credits. Default resolution is 720p.

Model	720p	1080p
kling-3.0-turbo	12/sec	15/sec
kling-v3	11/sec	14/sec
kling-v3 with audio: false	9/sec	12/sec
kling-v3-omni	9/sec	12/sec
kling-v3-omni with reference video (video_list)	11/sec	14/sec

Top-level resolution selects the quality tier.

Request fields

Send the common fields at the top level. Put the model-specific controls listed below inside providerOptions.

Field	Type	Required	Description
model	string	Yes	kling-3.0-turbo, kling-v3, kling-v3-omni
prompt	string	Yes	Describe subjects, actions, camera motion, and style; 1–2,000 characters on Pixapi.
seconds	integer	Yes	Integer 3–15 seconds; explicitly required.
resolution	string	No	720p / 1080p. Pixapi default: 720p.
n	integer	No	Default 1; only integer 1 is supported.
image	string / string[]	No	Turbo: one first frame. V3: one first frame or two images as first/last frames. Omni: references addressed in the prompt with <<<image_1>>>, <<<image_2>>>. Turbo input: JPEG/PNG ≤50 MB, each edge ≥300px, ratio 1:2.5–2.5:1.
providerOptions	object	No	Model-specific options; see the table below.

providerOptions

All fields in this table are nested inside providerOptions, not alongside model.

Field	Type	Description
aspect_ratio	string	16:9, 9:16, 1:1. Default 16:9; image-to-video follows the input image ratio.
audio	boolean	V3/Omni only; default false. Generate native sound. Do not combine Omni audio with video_list.
negative_prompt	string	V3/Omni: unwanted content; Omni maximum 2,500 characters.
image_with_roles	object[]	Omni: {url,role}, where role is first_frame, last_frame, or reference; do not also send top-level image.
video_list	object[]	Omni only; at most one {video_url,refer_type,keep_original_sound}. refer_type: base (edit, default) / feature (reference); sound: no (default) / yes. Base video: 3–10s, no first/last frames, output follows source duration. Feature video: MP4/MOV, ≥3s, 720–2160px, 24–60fps, ≤200MB.
multi_shot	boolean	V3/Omni: enable multiple shots; default false.
shot_type	string	V3/Omni: customize / intelligence; required when multi_shot=true.
multi_prompt	object[]	V3/Omni customized shots: 1–6 {index,prompt,duration} entries; index starts at 1, each duration ≥1, total equals top-level seconds; each prompt ≤512 characters.
element_list	object[]	V3/Omni: at most 3 subjects, each with name, description, element_input_urls (2–4 images). Reference subjects with @name in the prompt.
watermark	boolean	Add a visible AI watermark. Default false.
nsfw_check	boolean	Optional prompt/image moderation; default false.

Input rules

Pixapi supports 720p/1080p only. Use top-level resolution and seconds.

Example

cURL

curl https://api.pixapi.ai/v1/async/videos/generations \
  -H "Authorization: Bearer $PIXAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-3.0-turbo",
  "prompt": "A product spin on a clean studio turntable",
  "n": 1,
  "seconds": 5,
  "resolution": "720p",
  "providerOptions": {
    "aspect_ratio": "16:9"
  }
}'

Python

import os
import requests

response = requests.post(
    "https://api.pixapi.ai/v1/async/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['PIXAPI_KEY']}",
        "Content-Type": "application/json",
    },
    json={
    "model": "kling-3.0-turbo",
    "prompt": "A product spin on a clean studio turntable",
    "n": 1,
    "seconds": 5,
    "resolution": "720p",
    "providerOptions": {
        "aspect_ratio": "16:9"
    }
},
)
response.raise_for_status()
task = response.json()
print(task["id"])

JavaScript

const response = await fetch('https://api.pixapi.ai/v1/async/videos/generations', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.PIXAPI_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "kling-3.0-turbo",
  "prompt": "A product spin on a clean studio turntable",
  "n": 1,
  "seconds": 5,
  "resolution": "720p",
  "providerOptions": {
    "aspect_ratio": "16:9"
  }
}),
});

if (!response.ok) {
  throw new Error(await response.text());
}

const task = await response.json();
console.log(task.id);

Go

package main

import (
  "bytes"
  "fmt"
  "io"
  "net/http"
  "os"
)

func main() {
  body := []byte(`{
  "model": "kling-3.0-turbo",
  "prompt": "A product spin on a clean studio turntable",
  "n": 1,
  "seconds": 5,
  "resolution": "720p",
  "providerOptions": {
    "aspect_ratio": "16:9"
  }
}`)

  req, err := http.NewRequest(
    "POST",
    "https://api.pixapi.ai/v1/async/videos/generations",
    bytes.NewBuffer(body),
  )
  if err != nil {
    panic(err)
  }
  req.Header.Set("Authorization", "Bearer "+os.Getenv("PIXAPI_KEY"))
  req.Header.Set("Content-Type", "application/json")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
    panic(err)
  }
  defer resp.Body.Close()

  result, _ := io.ReadAll(resp.Body)
  fmt.Println(string(result))
}

Response

Pixapi returns a submitted task. Poll GET /v1/tasks/{id} for the final result.